Document AI Engineer

Key Responsibilities

 Design, deploy and maintain automated invoice extraction pipelines using GCP

Document AI.

 Develop custom model training workflows for documents with non-standard

formats.

 Preprocess and upload document datasets to Cloud Storage.

 Label documents using DocAI Workbench or JSONL for training.

 Train and evaluate custom processors using AutoML or custom schema

definitions.

 Integrate extracted data into downstream tools (e.g., BigQuery, ERP systems).

 Write robust, production-grade Python code for end-to-end orchestration.

 Maintain CI/CD deployment pipelines

 Ensure secure document handling and compliance with data policies.

Required Skills & Experience

 Strong hands-on experience with Google Cloud Platform, especially:

o Document AI

o Cloud Storage

o IAM

o Vertex AI (preferred)

o Cloud Functions / Cloud Run

 Proficient in Python, including Google Cloud SDK libraries

 Familiarity with OCR, and schema-based information extraction

 Understanding of security best practices for handling financial documents

Preferred Qualifications

 Previous projects involving invoice or document parsing

 Familiarity with BigQuery for analytics/reporting